The Agent Skills Directory

[SAFE]: No security issues detected. The skill implements a workflow for AI self-critique and evaluation using local scripts and templates.\n- [COMMAND_EXECUTION]: The included Python script rubric-scorecard.py is a local utility for calculating weighted scores. It uses standard libraries and does not invoke subprocesses or external commands.\n- [DATA_EXFILTRATION]: No network operations or data exfiltration patterns were identified. The skill operates entirely on local data.\n- [REMOTE_CODE_EXECUTION]: No remote code downloads or execution patterns are present.

agentic-eval